AI processors will lead the era of the Fourth Industrial Revolution
Artificial intelligence (AI) is one of the key emerging technologies. Global IT companies are competitively launching the newest technologies and competition is heating up more than ever. However, most AI technologies focus on software and their operating speeds are low, making them a poor fit for mobile devices. Therefore, many big companies are investing to develop semiconductor chips for running AI programs with low power requirements but at high speeds.
A research team led by Professor Hoi-Jun Yoo of the Department of Electrical Engineering has developed a semiconductor chip, CNNP (CNN Processor), that runs AI algorithms with ultra-low power, and K-Eye, a face recognition system using CNNP. The system was made in collaboration with a start-up company, UX Factory Co.
The K-Eye series consists of two types: a wearable type and a dongle type. The wearable type device can be used with a smartphone via Bluetooth, and it can operate for more than 24 hours with its internal battery. Users hanging K-Eye around their necks can conveniently check information about people by using their smartphone or smart watch, which connects K-Eye and allows users to access a database via their smart devices. A smartphone with K-EyeQ, the dongle type device, can recognize and share information about users at any time.
When recognizing that an authorized user is looking at its screen, the smartphone automatically turns on without a passcode, fingerprint, or iris authentication. Since it can distinguish whether an input face is coming from a saved photograph versus a real person, the smartphone cannot be tricked by the user’s photograph.
The K-Eye series carries other distinct features. It can detect a face at first and then recognize it, and it is possible to maintain “Always-on” status with low power consumption of less than 1mW. To accomplish this, the research team proposed two key technologies: an image sensor with “Always-on” face detection and the CNNP face recognition chip.
The first key technology, the “Always-on” image sensor, can determine if there is a face in its camera range. Then, it can capture frames and set the device to operate only when a face exists, reducing the standby power significantly. The face detection sensor combines analog and digital processing to reduce power consumption. With this approach, the analog processor, combined with the CMOS Image Sensor array, distinguishes the background area from the area likely to include a face, and the digital processor then detects the face only in the selected area. Hence, it becomes effective in terms of frame capture, face detection processing, and memory usage.
The second key technology, CNNP, achieved incredibly low power consumption by optimizing a convolutional neural network (CNN) in the areas of circuitry, architecture, and algorithms. First, the on-chip memory integrated in CNNP is specially designed to enable data to be read in a vertical direction as well as in a horizontal direction. Second, it has immense computational power with 1024 multipliers and accumulators operating in parallel and is capable of directly transferring the temporal results to each other without accessing to the external memory or on-chip communication network. Third, convolution calculations with a two-dimensional filter in the CNN algorithm are approximated into two sequential calculations of one-dimensional filters to achieve higher speeds and lower power consumption.
With these new technologies, CNNP achieved 97% high accuracy but consumed only 1/5000 power of the GPU. Face recognition can be performed with only 0.62mW of power consumption, and the chip can show higher performance than the GPU by using more power.
These chips were developed by Kyeongryeol Bong, a Ph. D. student under Professor Yoo and presented at the International Solid-State Circuit Conference (ISSCC) held in San Francisco in February. CNNP, which has the lowest reported power consumption in the world, has achieved a great deal of attention and has led to the development of the present K-Eye series for face recognition.
Professor Yoo said “AI – processors will lead the era of the Fourth Industrial Revolution. With the development of this AI chip, we expect Korea to take the lead in global AI technology.”
The Latest on: AI processor
Facebook wants to build its own processors for AI devices
on April 19, 2018 at 3:52 am
Facebook is the latest titan in the tech business to manifest interest in manufacturing its own processors, a practice that’s increasingly popular. Apple was one of the first companies to manufacture its own silicon, and its iPhone chips have been ... […]
Facebook set to form chip design team focused on AI – but why?
on April 19, 2018 at 3:43 am
The social network is recruiting people for a processor design team. Job listings reveal that the team will focus on AI, suggesting that it could be used in smart speakers. The company is hard at work on smart speakers already, but an in-house chip could ... […]
It looks like Facebook is preparing to build its own AI chips
on April 19, 2018 at 2:23 am
While little is known about how its own processors would be used ... and use their expertise to build custom solutions targeted at multiple verticals including AI/ML, compression, and video encoding. This position is full-time and located in our Menlo ... […]
Facebook Might Be Planning to Manufacture its Own Processors
on April 19, 2018 at 2:06 am
A system-on-chip or SoC is a processor used in mobile devices. An application-specific integrated-circuit or ASIC is a chip designed for a specific purpose. Google has also entered the hardware business and now develops its own AI chips. Apple has been ... […]
Microsoft Translator AI powers now work offline on mobile
on April 18, 2018 at 7:54 pm
Now, however, it has made enough optimizations that the same AI-powered offline language packs can be used on any phone with a powerful enough processor. And it’s a very low base if Amazon Fire devices are also supported. In addition, Microsoft is ... […]
Microsoft's AI-powered offline translation now runs on any phone
on April 18, 2018 at 3:15 pm
The feature was available on a handful of Android phones with AI chips before, but Microsoft has optimized the algorithms to run on most any modern phone's processor. The AI-capable offline packs are available in Translator's "most popular" languages ... […]
Facebook is just crazy enough to make its own processors
on April 18, 2018 at 3:02 pm
(SoC, or system-on-a-chip, is a processor typically designed for use in mobile devices; ASIC, or application-specific integrated circuit, is a chip designed for a particular purpose.) That role could oversee a team building chips for hardware, AI software ... […]
Microsoft Translator gets offline AI translations
on April 18, 2018 at 7:00 am
Menezes tells me that Microsoft first trialed these on-device neural translation with Huawei, which started including its homegrown AI co-processor in its Mate 10 and Honor 10 phones last year. Now, however, thanks to what Menezes called “a lot of ... […]
AI chips may give you a real reason to upgrade your smartphone
on April 15, 2018 at 5:00 am
Well, good news: The processor industry has noticed, too. That means we'll see a slew of new chips that should speed up AI tasks not just on your phone or laptop but also in your car or home security camera. It's just the latest development in AI. […]
New AI systems on a chip will spark an explosion of even smarter devices
on April 13, 2018 at 4:19 pm
Over the next several years, most new consumer devices will run AI natively, locally and, to an increasing extent, autonomously. But there’s a problem: Traditional processors in most mobile devices aren’t optimized for AI, which tends to consume a lot ... […]
via Google News and Bing News